Use Cline with BroadNet Inference (OpenAI Compatible provider)
Updated
In Cline settings, set API Provider to OpenAI Compatible, Base URL to https://inference.broadnet.ai/v1, API Key to your BroadNet key, and Model to a BroadNet ID such as broadnet/glm-5.3 or broadnet/deepseek-v4.1-flash. Then set the context window under Model Configuration so Cline knows how much it can send.
Cline is a coding agent that runs inside VS Code. It talks to any OpenAI-compatible API through its OpenAI Compatible provider, and BroadNet Inference uses the standard chat-completions shape at https://inference.broadnet.ai/v1. The steps below follow Cline’s own provider docs. If you prefer a terminal agent, see the Aider guide.
Setup
Get a key. Create a pay-as-you-go key in the BroadNet console, or buy an unlimited plan and use its plan key.
Open Cline settings. Click the gear icon in the Cline panel.
Choose the provider. In the API Provider dropdown, select OpenAI Compatible.
Fill in the connection fields.
Field
Value
Base URL
https://inference.broadnet.ai/v1
API Key
your BroadNet key
Model
broadnet/glm-5.3 (or another ID from the table below)
Set Model Configuration. Expand Model Configuration and enter the context window for the model you picked. Set Max Output Tokens high enough to leave room for reasoning; a few thousand tokens is a safe start. Turn on image support only for models that accept images. You can also enter input and output prices from the pricing page so Cline’s cost display is close to your bill.
Test it. Start a small task, such as “explain this file”. If it answers, the connection works.
Type the model ID exactly, including the broadnet/ prefix.
Which model to pick
Model
ID
Context
Good for
GLM 5.3
broadnet/glm-5.3
1,048,576
Agent work that depends on tool calls
DeepSeek V4.1 Flash
broadnet/deepseek-v4.1-flash
1,048,576
Long sessions on an unlimited plan; text and images
Qwen3.8 27B
broadnet/qwen3.8-27b
262,144
Tools plus images; Arabic text
BroadNet Gemma 4 VL 26B
broadnet/gemma-4-26b-a4b
32,768
Trying the setup on the free credit
BroadNet’s docs list tools and structured output for GLM 5.3 and Qwen3.8 27B. They don’t list tool calling for DeepSeek V4.1 Flash, so run a short real task on it before you commit to a month. A Meteor hour costs $1 and a Full Moon month $60; both are on the plans page. See the DeepSeek V4.1 Flash model page for details.
Troubleshooting
401 Unauthorized. The key is missing, wrong or expired, or a pay-as-you-go account has run out of allowance. Paste the key again and check the balance. Cline’s docs say to confirm the key belongs to the provider at the Base URL.
Model not found or the first request fails. Check the ID. It must match BroadNet’s model ID exactly. The paid models need a top-up; of the chat models, only broadnet/gemma-4-26b-a4b works on the free $5 credit.
Empty answer or a reply that stops early. Reasoning counts toward the output limit. Raise Max Output Tokens. Why answers come back empty.
429 Too Many Requests. A pay-as-you-go key allows 30 requests a minute and 4 in flight. Cline sends one request after another, so this usually means another app shares the key. See errors and retries.
Slow replies with several Cline windows. One plan session runs one request at a time. Two Cline tasks at once on one session queue behind each other. Buy one session per parallel task, or read running parallel coding agents on a flat rate.
Connection errors. Check that the Base URL ends in /v1 and that your network allows outbound HTTPS. If your key has an IP allow-list, add your machine’s address.
Questions
Why does Cline return an empty response?
The model spent its output budget on reasoning before writing the answer. DeepSeek V4.1 Flash, GLM 5.3 and Qwen3.8 27B reason first, and reasoning counts toward max_tokens. Raise Max Output Tokens in Model Configuration.
Can I run Cline on the unlimited plan?
Yes. The unlimited plans cover DeepSeek V4.1 Flash, model ID broadnet/deepseek-v4.1-flash. Use your plan key as the API Key. One Cline task uses one plan session.
Why doesn't the model list fill in by itself?
Type the model ID into the Model field. BroadNet's docs describe GET /v1/models as public catalog metadata for monitors, so don't rely on it to populate the picker.
Which BroadNet model works on the free starting credit?
Of the chat models, only BroadNet Gemma 4 VL 26B, model ID broadnet/gemma-4-26b-a4b; the credit also covers the two Transcribe models. The other chat models need a top-up. Its 32,768-token context is small for large repositories.